Students

Your Tasks

• Product development support
• Use case analysis and implementation
• Data analysis and evaluation
• Support in the extension of the existing product documentation
• Possibility to work in customer projects (semiconductor industry)

You also have the opportunity to find a topic for your thesis.

Your Profile

As a Project Management IT intern, you will have the following knowledge/background:

• C# programming skills
• Database (Ms-SQL)
• First experiences with data and process analysis
• Process modeling is an advantage
• Basic knowledge in the area of DataWarehouse
• Nice-to-have: Process knowledge in the area of semiconductor manufacturing

Your Tasks

• Unterstützung bei der Produktentwicklung
• Use-Case Analyse und Umsetzung
• Datenanalyse und Auswertung
• Unterstützung bei der Erweiterung der bestehenden Produktdokumentation
• Mitarbeit in Kundenprojekten (Halbleiterindustrie) möglich

Zusätzlich bieten wir Ihnen an, Ihre Abschlussarbeit bei uns zu schreiben.

Your Profile

Als Werkstudent Projektmanagement IT verfügen Sie über folgende Kenntnisse/Hintergrund:

• C# Programmierkenntnisse
• Datenbank (Ms-SQL)
• Erste Erfahrungen mit Daten- und Prozessanalyse
• Prozessmodellierung von Vorteil
• Grundkenntnisse im Bereich DataWarehouse
• Nice-to-have: Prozesskenntnisse im Bereich Halbleiterfertigung

Using kafka and AI to build the digital factory twin of the future

Streaming analytics allow to capture, aggregate and surface factory events at scale. In particular Apache Kafka has been shown to scale to millions of events per seconds. Within this project, we want to establish a data route from equipment in a semiconductor production environment into kafka. Using schema management, AI techniques and cloud BI, we will establish a real-time digital twin of production that allows drill-down to atomic production state-change.

Factory Simulation & Prediction: Playing What-if at scale to enable more throughput and higher tool utilization

Simulation Modelling is the key tool of Business Process Management (BPM) which comprises various methods to discover, model, analyze, measure, improve, optimize, and automate business processes. A simulation model of a production process is one of the most powerful enablers to boost operational efficiency, optimize resource usage, improve planning accuracy, or to grow a business.
In this project, we want to build on top of SYSTEMA's existing experience to model a bottleneck area in close collaboration with one of our industrial manufacturing partners.

Enable and facilitate root cause analysis in distributed manufacturing through log data classification

In highly automated factories, log data from tools and services accumulate with rates of several GB per minute. Deriving insights from these data remains a challenge task. Multiple problems need to be addressed. Do my logs contain unusual messages? 
How to enable structured log drilldown in distributed and highly dynamic manufacturing environments? How to avoid information overflow when interfacing with factoring staff through automated reporting?
In this internship the student will evaluate and implement methods to structure log data based on log content similarities and structural time series modeling. This will enable the detection of abnormal events such as rare tool states, unusual material routes or stalled processes. Suitable methods shall be condensed and implemented into a process to simplify root cause analysis. In addition, abnormal log events and their factory-wide aggregation shall be used to design a global anomaly score intended to streamline and simplify alerting. 

Material flow tracking at scale in semiconductor manufacturing

Keeping track of material in production is crucial to ensure high yield and low cycle times. To achieve this challenging goal in dynamic manufacturing environments, SYSTEMA has already developed a broad tooling portfolio, which partially addresses this problem.
In his internship, the student will help to research and implement novel methods to track material flow. After starting with data aggregation and enrichment over multiple sources to track material flow, he will investigate trend models to analyze anomalies and deviations in material transportation times. To embed these models into real-time streaming systems suitable architectural patterns shall be developed. Finally, these data shall be condensed into a monitoring & reporting tool for transportation system load monitoring and trend analysis.

Event Detection for Multivariate IIoT Sensor Data Streams

The reliable detection of transitions between appliance states in multivariate sensor signals is fundamental to the adoption of Machine Learning methods in industrial IoT. As state transition detection allows a discretization of appliance states, it precedes downstream categorization and integration. Thus, the detection of these transition events is key towards improved manufacturing decision intelligence solutions.
During this internship, the student will assess and extract a suitable set of event detection methods to cover typical sensor readings in iIoT. Next, she will implement these methods within a real-time streaming architecture (such as logstash, kafka, TimeScaleDB). Along with that, requirements for a user interface approach to select appropriate methods in a semi supervised way shall be addressed.